Research map / Large language models / Language, safety and interpretability
Textual Bayes: Quantifying Uncertainty in LLM-Based Systems
Brendan Leigh Ross, Noël Vouitsis, Atiyeh Ashari Ghomi, Rasa Hosseinzadeh, Ji Xin, Zhaoyan Liu, Yi Sui, Shiyi Hou, Kin Kwan Leung, Gabriel Loaiza-Ganem, Jesse C. Cresswell
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| sample prompts with MHLP instead of TextGrad alone | MHLP (GPT-4o / GPT-4o-mini) · AIME 2024, SimpleQA, QASPER | accuracy and ECE | Improved |
| use MHLP instead of calibrated baselines on AIME | MHLP · AIME 2024 | ECE | Hurt |
| use MHLP prompt samples for conformal factuality frequency scoring instead of a fixed GPT-4 prompt | MHLP frequency scoring · FactScore (person biographies) | claim removal rate | Improved |
| use MHLP vs TextGrad on an unanswerable QASPER example (random context) | MHLP · QASPER (random context) | answers in 'Unclear / not specified' cluster out of 10: 0 -> 6 | Improved |
Closest papers by meaning
- SPANUQ: Span-Level Uncertainty Quantification for Large Language Model Generation (NeurIPS 2026 · similarity 0.90)
- Large Language Models to Enhance Bayesian Optimization (ICLR 2024 · similarity 0.90)
- Benchmarking LLMs via Uncertainty Quantification (NeurIPS 2024 · similarity 0.90)
- Large Language Models Must Be Taught to Know What They Don’t Know (NeurIPS 2024 · similarity 0.90)
- Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification (NeurIPS 2026 · similarity 0.89)
- BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models (ICLR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
